INDEX

Explanations

words related to positivity or positive attributes

oai_token-act-pair · gpt-3.5-turbo

words related to positivity and positive sentiment

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å£«

-0.71

ERA

-0.69

åŃ

-0.69

EVA

-0.69

æĸ¹

-0.68

 Recall

-0.68

tracks

-0.67

Fug

-0.67

masters

-0.67

channelAvailability

-0.66

POSITIVE LOGITS

sembly

0.88

ilon

0.87

pos

0.84

ples

0.84

essions

0.82

pled

0.80

ffer

0.80

cess

0.79

atile

0.79

alty

0.78

Activations Density 0.031%

words related to positivity or positive attributes

words related to positivity and positive sentiment

No Comments

No Known Activations